A subset of compute nodes in the us-east-1 region is experiencing increased cold start times.
Resolved
Updates
Resolved
Fix was deployed to all regions and this incident has been resolved.
Investigating
Investigating: (17:02) We are currently investigating this incident. Monitoring: (20:17) We have identified the root cause of the issue and have developed a fix. The problem only affects the initial connection attempt since our most recent deployment, causing it to be slow. Fortunately, most of the endpoints have already reconnected, so we assess the current impact to be low. We're conducting additional internal testing on the fix and aim to deploy it within the next 24 hours.